• merc@sh.itjust.works
    link
    fedilink
    arrow-up
    3
    ·
    22 days ago

    They already do gait analysis

    Are you sure? As far as I’ve seen that’s just pop sci-fi bullshit that has never been proven to work in the real world.

      • merc@sh.itjust.works
        link
        fedilink
        arrow-up
        3
        ·
        22 days ago

        This paper makes it sound like it’s still basically guesswork. It’s a lot like lie detector tests. They don’t really work, but maybe they can be somewhat useful tools when combined with lots of other things?

        • KairuByte@lemmy.dbzer0.com
          link
          fedilink
          arrow-up
          3
          ·
          22 days ago

          I want to preface this with: I agree with you.

          But the success of most things algorithm related are nowhere near 100%. Look at facial recognition, or even fingerprint recognition. There are false positives, to the point that innocent people have been convicted on them.

          All tech has a margin of error, and it’s us idiots (meaning humans in general) that place an oversized trust in it.

          • merc@sh.itjust.works
            link
            fedilink
            arrow-up
            1
            ·
            22 days ago

            There’s a difference between things that are based in sound science but aren’t 100% accurate, and things that are based on, at best, untested hypotheses.

            I’d put gait analysis along with things like bite mark analysis, phrenology, etc. The appropriate level of trust in it is near zero percent. But, largely because it’s expensive, people convince themselves that something that expensive has to work. It’s similar to a lie detector test. They strap so many different things to you to measure your body, and have an expert in the machine who studies what’s happening. That leads people to believe that it has to work, at least a bit. But, there’s a reason why lie detector tests are generally not admissible in court. Even though they genuinely can tell… something, the potential for them to be misunderstood by the jury is too high for them to be allowed into evidence.

        • Cherries@lemmy.world
          link
          fedilink
          arrow-up
          1
          ·
          21 days ago

          Police already arrest the wrong people, even when they have the name and address for a warrant. Even when the person doesn’t match the picture they are given, police lock 'em up anyway.

          Unfortunately, it doesn’t matter how accurate stuff like this is; it’ll just be another tool assholes, not just the police, use to justify being mean to people they don’t like.